Sanctum
  • ✨Overview
  • 🖥️System Requirements
  • 🔐Architecture & Privacy
  • 📂File manager
  • ⌨️Keyboard Shortcuts
  • MODELS
    • ⚙️Models Management
    • ⚡Model Performance
    • 📦Toolbox
  • DEV MODE
    • 🛠️Advanced Model Settings
    • 🗄️Local Server
  • USEFUL LINKS
    • ⬇️Download Sanctum
    • ✖️Join us on X
    • 👀Join us on Discord
Powered by GitBook
On this page

Was this helpful?

  1. DEV MODE

Local Server

Start a local HTTP server that mimics OpenAI's API functionality, allowing you to test and interact with your application locally.

PreviousAdvanced Model Settings

Last updated 5 months ago

Was this helpful?

To access the Local Server page, make sure that Developer Mode is enabled. If it is not already active, activate it by clicking the Developer Mode toggle located in the bottom-left corner. Then navigate to the Local Server page by selecting the code icon in the left sidebar.

Configuration Options

The Local Server page provides several settings to configure how the server operates.

Parameters
Description

Server port

Defines the port number the server uses to listen for incoming connections, enabling client access via the specified port.

Verbose Server Logs

Activates detailed token predictions in server logs unless streaming is enabled.

Apply Prompt Formatting

This setting adjusts to different formatting requirements of various models. When enabled, prompt prefixes/suffixes are automatically handled.

Share to Local Network

Enable connections from other devices within the local network. When disabled, the server will only be accessible on localhost.

🗄️